XianyanLin
大家都是中国人 我说中文好了 这样能更好地表达我的意思 避免表达不清造成歧义 1. 我在学习你的代码 这样对我理解论文本身有很大的好处 感谢你能够把你的代码开源出来！帮助到更多的人 2. 我想把这个项目使用到单片机上，最后测试部分的代码，应该是要移植到C上面，但是不知道这个算法的速度怎么样？我把opencv的VJ检测器简化移植到单片机上面是可以运行的 虽然达不到实时性 另外我所使用的单片机是stm32f429z 3. 如果速度上，JDA单和VJ检测器比较如何？
I found that I cannot use release version of `caffe.dll` and `caffe.lib` when I try to debug my project. It is a good idea to set postfix `d` to distinguish...
Did you only use the cpu of pi3 to run MTCNN ?
What's the problem ? ``` λ websploit ____ __ ____ \ \ / \ / / | Welcome to Websploit \ \/ \/ / | Version : 4.0.4 \ /...
I have run your code, but I found the performance has some gap between these cpp and py version. ``` 1. the cpp version has a better scale invariance 2....
it might be `epoch[1]` [here](https://github.com/Seanlinx/mtcnn/blob/master/demo.py#L31) ``` # load rnet model args, auxs = load_param(prefix[1], epoch[0], convert=True, ctx=ctx) ```
I noted that you did little effort on data augmentation, and this is the end of the training of pnet: ``` INFO:root:Epoch[15] Train-Accuracy=0.931125 INFO:root:Epoch[15] Train-LogLoss=0.206840 INFO:root:Epoch[15] Train-BBOX_MSE=0.015009 INFO:root:Epoch[15] Time cost=118.500...
I found it that you models are slower then the official release. Did you retrained all models ?
I have trained a mobilenet based ssd from scratch using `trainval set in VOC2007/2012`. Now it has an mAP at 0.425539 and seems hard to make large improvement. It might...
I found that PreluPlugin still need a constructor for nvinfer1::Weights to init prelu parameters